Downloads · 30 days
12
17% of all-time downloads
lilt-roberta-en-base-finetuned-funsd
clabluo/lilt-roberta-en-base-finetuned-funsd
lilt-roberta-en-base-finetuned-funsd is a token classification model from clabluo. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
70
Public
Parameters
130M
2.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors521 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- lilt
- Access
- Public
- Created
- Mar 10, 2025
- Updated
- Mar 10, 2025
- SHA
- c15f182f
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
lilt-roberta-en-base-finetuned-funsd
This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5942
- Precision: 0.8678
- Recall: 0.8967
- F1: 0.8820
- Accuracy: 0.8107
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 60
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 5.2632 | 100 | 0.7530 | 0.8051 | 0.8559 | 0.8298 | 0.7870 |
| No log | 10.5263 | 200 | 0.9869 | 0.8232 | 0.8490 | 0.8359 | 0.7906 |
| No log | 15.7895 | 300 | 1.1115 | 0.8653 | 0.8773 | 0.8712 | 0.8076 |
| No log | 21.0526 | 400 | 1.2245 | 0.8313 | 0.8544 | 0.8427 | 0.7940 |
| 0.2553 | 26.3158 | 500 | 1.3779 | 0.8733 | 0.8798 | 0.8765 | 0.8073 |
| 0.2553 | 31.5789 | 600 | 1.4417 | 0.8690 | 0.8733 | 0.8712 | 0.8071 |
| 0.2553 | 36.8421 | 700 | 1.6714 | 0.8571 | 0.8793 | 0.8681 | 0.7929 |
| 0.2553 | 42.1053 | 800 | 1.5601 | 0.8713 | 0.8977 | 0.8843 | 0.8057 |
| 0.2553 | 47.3684 | 900 | 1.6547 | 0.8709 | 0.8912 | 0.8809 | 0.7965 |
| 0.0071 | 52.6316 | 1000 | 1.6069 | 0.8746 | 0.8872 | 0.8809 | 0.8003 |
| 0.0071 | 57.8947 | 1100 | 1.6732 | 0.8451 | 0.8887 | 0.8663 | 0.7912 |
| 0.0071 | 63.1579 | 1200 | 1.5469 | 0.8688 | 0.8917 | 0.8801 | 0.8076 |
| 0.0071 | 68.4211 | 1300 | 1.5922 | 0.8746 | 0.8972 | 0.8857 | 0.8017 |
| 0.0071 | 73.6842 | 1400 | 1.5249 | 0.8694 | 0.8992 | 0.8840 | 0.8120 |
| 0.0014 | 78.9474 | 1500 | 1.6120 | 0.8611 | 0.9026 | 0.8814 | 0.8047 |
| 0.0014 | 84.2105 | 1600 | 1.6198 | 0.8696 | 0.9041 | 0.8865 | 0.8080 |
| 0.0014 | 89.4737 | 1700 | 1.6202 | 0.8694 | 0.9026 | 0.8857 | 0.8136 |
| 0.0014 | 94.7368 | 1800 | 1.6261 | 0.8521 | 0.8927 | 0.8719 | 0.8007 |
| 0.0014 | 100.0 | 1900 | 1.5935 | 0.8689 | 0.8957 | 0.8821 | 0.8110 |
| 0.0005 | 105.2632 | 2000 | 1.5942 | 0.8678 | 0.8967 | 0.8820 | 0.8107 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Task
- Token Classification
- Library
- transformers
- Type
- lilt
- License
- mit
- Created
- Mar 10, 2025
- Updated
- Mar 10, 2025